No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by Ancienttwo · Codex Skill · ★ 435
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is repo-harness safe to install? View the security audit →
repo-harness turns Claude/Codex coding sessions into a repeatable repo-local workflow. It ships a CLI plus skill/runtime hooks that write context, plans, handoffs, checks, and review evidence back into the project, so the next agent session can continue from files instead of chat memory. Use it to: adopt an existing repo with a tasks-first agent contract keep Claude and Codex aligned on the same plans, checks, handoffs, and context boundaries spend fewer tokens rediscovering structure by using CodeGraph and progressive context loading Give the agent a complete PRD or Sprint; after that, your loop is just review and , or start and go AFK. Repository: English Español Why repo-harness File-backed sessions, not chat memory. Separate agent sessions — Claude and Codex, now and later — stay coordinated through the repo, not a thread. injects the prior session's resume packet (, ) when a new session starts; writes the stop handoff, while refreshes edit-time traces
| Stars | 435 |
| Forks | 33 |
| Language | TypeScript |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 66.1263009781651/100 |
| Last Updated | 2026-09-18 |
| Created | 2026-03-19 |
| Platforms | claude-code, codex, node |
| Est. Tokens | ~25k |
These tools work well together with repo-harness for enhanced workflows:
Looking for a repo-harness alternative? If you're comparing repo-harness with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
The skill layer for AI agents: npm for AI Agent Skills.
Native, local-first knowledge graph engine for code and project artifacts—inspired by Graphify, built in Rust,
Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server
DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent
Portable SKILLs workspace for Claude Code, Codex, and Gemini — issue-driven workflows and cross-agent collabor
Professional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software
Explore other popular codex skill tools:
repo-harness is File-backed workflow harness for reliable Claude Code and Codex sessions.. It is categorized as a Codex Skill with 435 GitHub stars.
repo-harness is primarily written in TypeScript. It covers topics such as agentic-workflows, ai-agents, claude-code.
You can find installation instructions and usage details in the repo-harness GitHub repository at github.com/Ancienttwo/repo-harness. The project has 435 stars and 33 forks, indicating an active community.
repo-harness is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to repo-harness on Agent Skills Hub include openagentskill, compass, Overture. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: